Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c96db62fb0ba1bd462fe276e12eb10149cbcd2058d9f44092acad8ba721e532e
+oid sha256:6b11c00fdaa960c8158fdcfccedd133b02db62752eea12a76237ce18cb4e61a6
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5130d75ef58c57e5c16e84ea3f0e4ad00577e95c9ed785800e53d22c74ae970
+oid sha256:e263e4742cc273da403aa023f726d4289dc526dc607369f88bbca90ad1838a8f
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64b4eb4fc97dc920d8a3f9cd0bf7bf6acabfbcb9882dfb612615f8761447388
+oid sha256:935e4fc8e16227ac7787c3b30e200a334ade209c6e028204415130045cef6ef8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50560a092f780774261595a92e46585ee289404a3dfdf790ba7c86823bfa4a2b
+oid sha256:6a2f370fc2662683d37d65c83dcc7375f77b9a2adec415cd67fffb3ded951c23
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52884ae0762e1bafe1de26f4b9e67057dfc03e49eb253c07f05333f81480a03f
+oid sha256:c76a604f9874b85def3e9923b59c88d845df0295612811052e801728afe0427b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6624d3d0dbd9ca66587a9042a9e9ccffa1ab07988396582e70b5777e09bb0ac7
+oid sha256:e92f4d4e63b747332866df1b9dca3fb40c5d31cd80a5bbd0d5205c29ddef5a78
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9995794296264648,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007199553627675084,
+  "best_metric": 0.9675429463386536,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.014399107255350168,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 17.798,
       "eval_steps_per_second": 2.225,
       "step": 25
+    },
+    {
+      "epoch": 0.0074875357727820875,
+      "grad_norm": 0.1074371486902237,
+      "learning_rate": 5e-05,
+      "loss": 0.6208,
+      "step": 26
+    },
+    {
+      "epoch": 0.007775517917889091,
+      "grad_norm": 0.13460542261600494,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7484,
+      "step": 27
+    },
+    {
+      "epoch": 0.008063500062996094,
+      "grad_norm": 0.14959374070167542,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7917,
+      "step": 28
+    },
+    {
+      "epoch": 0.008351482208103098,
+      "grad_norm": 0.18210013210773468,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7766,
+      "step": 29
+    },
+    {
+      "epoch": 0.008639464353210101,
+      "grad_norm": 0.2088140994310379,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7724,
+      "step": 30
+    },
+    {
+      "epoch": 0.008927446498317105,
+      "grad_norm": 0.21003039181232452,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8387,
+      "step": 31
+    },
+    {
+      "epoch": 0.009215428643424107,
+      "grad_norm": 0.19656838476657867,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8587,
+      "step": 32
+    },
+    {
+      "epoch": 0.00950341078853111,
+      "grad_norm": 0.22205334901809692,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8314,
+      "step": 33
+    },
+    {
+      "epoch": 0.009791392933638114,
+      "grad_norm": 0.22005382180213928,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8041,
+      "step": 34
+    },
+    {
+      "epoch": 0.010079375078745118,
+      "grad_norm": 0.2383647859096527,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0052,
+      "step": 35
+    },
+    {
+      "epoch": 0.010367357223852122,
+      "grad_norm": 0.3092731535434723,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1196,
+      "step": 36
+    },
+    {
+      "epoch": 0.010655339368959125,
+      "grad_norm": 0.39753103256225586,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1256,
+      "step": 37
+    },
+    {
+      "epoch": 0.010943321514066127,
+      "grad_norm": 0.08987879753112793,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6193,
+      "step": 38
+    },
+    {
+      "epoch": 0.01123130365917313,
+      "grad_norm": 0.11447886377573013,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6659,
+      "step": 39
+    },
+    {
+      "epoch": 0.011519285804280134,
+      "grad_norm": 0.11815035343170166,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6756,
+      "step": 40
+    },
+    {
+      "epoch": 0.011807267949387138,
+      "grad_norm": 0.15227173268795013,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8462,
+      "step": 41
+    },
+    {
+      "epoch": 0.012095250094494142,
+      "grad_norm": 0.14129722118377686,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7612,
+      "step": 42
+    },
+    {
+      "epoch": 0.012383232239601145,
+      "grad_norm": 0.16149425506591797,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7903,
+      "step": 43
+    },
+    {
+      "epoch": 0.012671214384708147,
+      "grad_norm": 0.1861640214920044,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.784,
+      "step": 44
+    },
+    {
+      "epoch": 0.012959196529815151,
+      "grad_norm": 0.18323907256126404,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8417,
+      "step": 45
+    },
+    {
+      "epoch": 0.013247178674922155,
+      "grad_norm": 0.2482207715511322,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8842,
+      "step": 46
+    },
+    {
+      "epoch": 0.013535160820029158,
+      "grad_norm": 0.24446065723896027,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8933,
+      "step": 47
+    },
+    {
+      "epoch": 0.013823142965136162,
+      "grad_norm": 0.2554016709327698,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9438,
+      "step": 48
+    },
+    {
+      "epoch": 0.014111125110243166,
+      "grad_norm": 0.3131295442581177,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9895,
+      "step": 49
+    },
+    {
+      "epoch": 0.014399107255350168,
+      "grad_norm": 0.37427470088005066,
+      "learning_rate": 0.0,
+      "loss": 1.1602,
+      "step": 50
+    },
+    {
+      "epoch": 0.014399107255350168,
+      "eval_loss": 0.9675429463386536,
+      "eval_runtime": 921.6436,
+      "eval_samples_per_second": 25.382,
+      "eval_steps_per_second": 3.174,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3469808143735194e+17,
+  "total_flos": 2.6947910513564058e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null